Last year’s Envirocon was a huge success and was very well received by those attending. This year’s conference will also be dedicated to new technology in the environmental monitoring sector, however, it will have a slightly different format. The morning session will be dedicated to presentations and speakers, and in the afternoon there will be a workshop.
- Wayne Jones, Shell
- Paul Drury, Ambiental
- Andy Hughes, Willowstick
- Karl Daines, SGS
- Steve Wilson, EPG
- Andrew Porter, WSP
Lunch & Networking
Presentation: Applying Data Analytics & AI to environmental analytics by Maryam Hussein
The era of digitization is here, and the environmental industry is more than ready for a fresh approach. Environmental practitioners are exploring how to leverage technologies and methodologies in order to harness insights based on environmental data. Also, employers are now empowering their employees to make this change.
This is coupled with the belief that the next step for a company is to leverage this data as they move along the path to digital ascendancy in order to improve efficiency and accuracy of risk assessment and speed up project delivery.
This presentation covers all aspects and subject areas that must be considered and explored on this journey. Case studies and examples will be presented and discussed how the application of analytics and the build of a system of intelligence has and can transform the assessment and management of environmental risk.
Workshop: 10 Data & Analytics Techniques to automate and accelerate environmental analysis
This workshop takes a hands-on and engaged approach to present, discuss and explore the 10 most important considerations, techniques and methodologies to automate and accelerate environmental data analysis.
2 example techniques:
Partial Dependency Analysis
The partial dependence plot (short PDP or PD plot) shows the marginal effect one or two features have on the predicted outcome of a machine learning model.
A partial dependence plot can show whether the relationship between the environmental metric and other selected data variables is linear, monotonous or more complex.
To perform seasonality analysis, time series decomposition transforms a time series data set into multiple different time-series data sets, while the original time series is often split into 3 component series:
- Seasonal: Patterns that repeat with a fixed period of time. For example, a tidal gauge will receive more a higher reading every 7 days; this would produce data with seasonality of 7 days.
- Trend: The underlying trend of the metrics. A gauge continuously increasing should show a general trend that goes up.
- Random: Also call “noise”, “irregular” or “remainder,” this is the residuals of the original time series after the seasonal and trend series are removed.
Attendees are encouraged to contact the speaker up to 2 weeks in advances of the workshop with specific case studies and data that will be worked through in the case study.
Reception & Refreshments
Read what our attendees thought about the previous Envirocon
Tony Windsor, Associate Technical Director – Site Evaluation & Restoration
Paul Nathanail, Managing Director
Land Quality Management
Geraint Williams, Associate
The conference provided an excellent opportunity to catch up with the industry professionals. Let’s not forget the great spot for networking afterwards.
For the first time, it has definitely raised the bar.”